© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49528
    Prev
    Next
    INDEX
    Explanations

    call, dial, inform, access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /email
    -0.12
     Skype
    -0.11
     email
    -0.10
     skype
    -0.10
     communications
    -0.10
     Gmail
    -0.09
     messenger
    -0.09
     emails
    -0.09
     sit
    -0.09
     telegram
    -0.09
    POSITIVE LOGITS
     callers
    0.16
     dial
    0.14
     caller
    0.14
     Caller
    0.14
     dia
    0.14
     Dial
    0.12
     hanging
    0.12
     toll
    0.12
     statewide
    0.12
     beep
    0.11
    Activations Density 0.067%

    No Known Activations